Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses cost, prerequisites, size limits, and billing semantics: 300 micro-dollar credits per successful call, requires credits/Authorization header, up to 50 blocks, and a new requestId is a new billable operation. These details go well beyond the annotations and are consistent with idempotentHint=true because reusing a requestId enables recovery without new billing.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loaded: the core function appears in the first sentence, followed by cost, prerequisite, and recovery notes. Every sentence delivers operationally useful information without repetition or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present and three parameters documented in the schema, the description supplies the missing operational context: billing, auth prerequisites, preparation step, block limit, and recovery semantics. An agent has enough information to invoke the tool correctly and understand the consequences of doing so.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds practical meaning to requestId and maxPriceMicroUsd by framing them around recovery and billing, and the first sentence clarifies that the input is HTML to be parsed. The schema already documents requestId and maxPriceMicroUsd, while the nested input.html field's semantic role is implied by the tool's stated purpose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Parse up to 50 JSON-LD blocks from supplied HTML.' This clearly differentiates html_jsonld from the many sibling HTML tools like html_metadata, html_tables, and html_feeds, which target other extraction tasks.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit operational guidance: call agent_utilities_prepare first, ensure existing credits and a private Authorization header, and reuse prepared arguments for recovery. It does not explicitly list 'when not to use' an alternative, but the unique JSON-LD extraction scope supplies enough routing context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.